Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.8001. Min Act: -0.0001

Data Index: 545210 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.7926. Min Act: -0.0001

Data Index: 981303 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.7441. Min Act: -0.0001

Data Index: 1024650 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1341574 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1043633 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6556. Min Act: -0.0001

Data Index: 197125 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5997. Min Act: -0.0001

Data Index: 731543 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1175238 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5837. Min Act: -0.0001

Data Index: 867480 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5810. Min Act: -0.0001

Data Index: 1305147 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6008. Min Act: -0.0001

Data Index: 1151277 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1278578 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5599. Min Act: -0.0001

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5654. Min Act: -0.0001

Data Index: 957462 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5370. Min Act: -0.0001

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.4835. Min Act: -0.0001

Data Index: 1505182 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5130. Min Act: -0.0001

Data Index: 638752 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5274. Min Act: -0.0001

Data Index: 1376109 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.5090. Min Act: -0.0001

Data Index: 753064 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.8001. Min Range: -0.8001

Max Act: 0.4873. Min Act: -0.0001

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 687